__/ [ Handover Phist ] on Thursday 31 August 2006 17:59 \__
> Roy Schestowitz :
>> Announcing Tesseract OCR
>>
>> ,----[ Quote ]
>>| We wanted to let you all know that a few months ago we quietly released -
>>| or actually re-released - an Optical Character Recognition (OCR) engine
>>| into open source.
>> `----
>>
>>
http://google-code-updates.blogspot.com/2006/08/announcing-tesseract-ocr.html
>>
>> Picasa and Google Earth (among other applications) were not Open Source.
>> This code might help existing OS OCR projects, which many Linux newbies
>> still nag about (among other areas: voice recognition, games, and Adobe
>> Photoshop).
>
> Not just newbies have been complaining about the lack of OCR, I myself
> have commented on it and have been waiting a good long time for a
> project like this to grow.
>
> For those who would say "Why didn't you just code one up yourself?", I'm
> just not that good a coder.
>
> This announcement makes me extremely happy.
I am aware of (at least two) projects that have a decent graphical users
interface and perform all right. I never tried them myself though. Either
way, performance-wise, they could improve by plugging Google's code in
(assuming licenses permit this). I imagine that Google developed (or
acquired) something beyond satisfactory to have Google Print developed and
flourish. It is, after all, yet to become a threat to Amazon's large empire,
in my humble opinion.
Best wishes,
Roy
--
Roy S. Schestowitz | FreeBSD - sidling with a little devil
http://Schestowitz.com | GNU/Linux | PGP-Key: 0x74572E8E
Swap: 1036184k total, 238264k used, 797920k free, 50160k cached
http://iuron.com - next generation of search paradigms
|
|